发明名称 Systems and methods that generate height map models for efficient three dimensional reconstruction from depth information
摘要 Methods of generating a three dimensional representation of an object in a reference plane from a depth map including distances from a reference point to pixels in an image of the object taken from a reference point. Weights are assigned to respective voxels in a three dimensional grid along rays extending from the reference point through the pixels in the image based on the distances in the depth map from the reference point to the respective pixels, and a height map including an array of height values in the reference plane is formed based on the assigned weights. An n-layer height map may be constructed by generating a probabilistic occupancy grid for the voxels and forming an n-dimensional height map comprising an array of layer height values in the reference plane based on the probabilistic occupancy grid.
申请公布号 US9208612(B2) 申请公布日期 2015.12.08
申请号 US201113578758 申请日期 2011.02.11
申请人 The University of North Carolina at Chapel Hill;Eidgenossische Technische Hochschule Zurich 发明人 Frahm Jan-Michael;Pollefeys Marc Andre Leon;Gallup David Robert
分类号 G06T15/06;G06T17/05;G06T17/00 主分类号 G06T15/06
代理机构 Jenkins, Wilson, Taylor & Hunt, P.A. 代理人 Jenkins, Wilson, Taylor & Hunt, P.A.
主权项 1. A method of generating a three dimensional representation of an object in a reference plane, comprising: providing a two dimensional grid of cells that define the reference plane in which at least a portion of the object is located; providing a three dimensional grid of voxels that define a physical volume above the two-dimensional grid of cells; providing a depth map in a processing unit, the depth map comprising distances from a reference point to pixels in an image of the object taken from the reference point, wherein the pixels in the image correspond to features of the object visible in the image; assigning weights in the processing unit to respective ones of the voxels in the three dimensional grid along rays extending from the reference point through the pixels in the image based on the distances in the depth map from the reference point to the respective pixels, wherein a weight value for a voxel is assigned based on whether a depth value for a pixel is greater than or less than or equal to a depth value for the voxel along one of the rays; and forming, from the depth map, a height map in the processing unit, the height map comprising an array of height values in the reference plane based on the assigned weights.
地址 Chapel Hill NC US